gary083 / GAN_Harmonized_with_HMMs
Code:Completely Unsupervised Speech Recognition By A Generative Adversarial Network Harmonized With Iteratively Refined Hidden Markov Models
☆24Updated 4 years ago
Related projects: ⓘ
- ☆31Updated 3 years ago
- ☆10Updated 5 years ago
- PyTorch implementation of: Rhythm-Flexible Voice Conversion without Parallel Data Using Cycle-GAN over Phoneme Posteriorgram Sequences☆11Updated 5 years ago
- Reproducing Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis (https://arxiv.org/pdf/1803.09…☆61Updated 6 years ago
- TensorFlow Implementation of CDVAE-VC.☆54Updated last year
- ☆15Updated 3 years ago
- ☆22Updated 4 years ago
- ☆22Updated 5 years ago
- ☆20Updated 3 years ago
- ☆23Updated this week
- A PyTorch implementation of the universal neural vocoder☆66Updated 3 years ago
- Non-Autoregressive Predictive Coding☆50Updated 3 years ago
- ☆34Updated 4 years ago
- ☆10Updated 2 years ago
- Tacotron2 with Global Style Tokens☆61Updated 5 years ago
- Gaussian Mixture VAE Tacotron☆52Updated last year
- An implementation of SkipVQVC with various settings.☆75Updated 4 years ago
- Stellenbosch University ZeroSpeech 2019 System☆10Updated 5 years ago
- DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.☆13Updated last year
- ☆69Updated this week
- ☆96Updated 3 years ago
- A Pytorch implementation for the ZeroSpeech 2019 challenge.☆111Updated 4 years ago
- ☆51Updated 5 years ago
- An evaluation toolkit for voice conversion models.☆39Updated 3 years ago
- Pytorch implementation of Generalized End-to-End Loss for speaker verification☆80Updated 5 years ago
- Official Implementation of SERIL in Pytorch☆26Updated 3 years ago
- My vim comfiguration☆43Updated last week
- AudioCodec-Hub is a Python library for encoding and decoding audio data, supporting various neural audio codec models☆21Updated 11 months ago
- Speech (audio) subjective evaluation system☆37Updated 4 years ago
- Textless (ASR-transcript free) Spoken Question Answering. The official release of NMSQA dataset and the implementation of "DUAL: Textless…☆34Updated last year